Facebook has unveiled a cutting-edge computer vision algorithm that can identify individuals in pictures even if some of those individuals are facing away from the camera, New Scientist reports.
Computer vision algorithms currently suggest tags for photos uploaded to the social network, but the latest exhibition of Facebook’s technology at the Computer Vision and Pattern Recognition conference in Boston managed to identify people in 40,000 public Flickr photos with 83% accuracy. Even more uncanny, the algorithm was able to seize on unique identifying traits, such as hairstyles and recurring outfits.
“People have characteristic aspects, even if you look at them from the back,” Facebook’s head of artificial intelligence told New Scientist. “For example, you can recognize Mark Zuckerberg very easily because he always wears a gray T-shirt.”
It isn’t yet clear if the new algorithm will be incorporated into any of Facebook’s products.
Facebook’s Gorgeous New Campus Has a ‘Green Roof’ the Size of 7 Football Fields
More Must-Reads from TIME
- Introducing the 2024 TIME100 Next
- Sabrina Carpenter Has Waited Her Whole Life for This
- What Lies Ahead for the Middle East
- Why It's So Hard to Quit Vaping
- Jeremy Strong on Taking a Risk With a New Film About Trump
- Our Guide to Voting in the 2024 Election
- The 10 Races That Will Determine Control of the Senate
- Column: How My Shame Became My Strength
Contact us at letters@time.com